• Aditi Anil Patil
• Dipti Patil
• Shivani Suryawanshi
• Rutuja Sonawane
• Mehzabin Shaikh

As the ever-growing segment of people uses social media in their daily lives, social media is analyzed in many different fields. The process of analyzing social media involves four distinct stages, data acquisition, collection, optimization, and analysis. Social media analytics is the process of collecting hidden information from social data - both formal and informal - to allow informed decision-making. Recommendation systems are widely used on the web to recommend products and services to users. Most e-commerce sites have such systems. But here social media platform is something we plan to do data analysis on. We know somehow Instagram, Facebook, etc are being used for this, but photos or via posts as a dataset. Here description using hashtags is something new we are going to try as a source for recommending products. As the hashtag labels used on social media sites make it easy to find specific themes or content and are used not only to describe the visual content of an image but also serve other functions falling under the meta-communicative use or describing things. This paper proposes a one-of-a-kind recommendation system through data analysis on social media where we are extracting new datasets like keywords including hashtags, which are further used to recommend similar products.

Hashtags, pre-processing, web scraping, classification, clustering, feature Extraction K-Nearest Neighbour (KNN).

"Social Media Data Analysis", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 7, page no.a745-a750, July-2021, Available :http://www.jetir.org/papers/JETIR2107095.pdf

"Social Media Data Analysis", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 7, page no. ppa745-a750, July-2021, Available at : http://www.jetir.org/papers/JETIR2107095.pdf